English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Deep neural networks (DNNs), especially convolutional neural networks, haveachieved superior performance on image classification tasks. However, suchperformance is only guaranteed if the input to a trained model is similar tothe training samples, i.e., the input follows the probability distribution ofthe training set. Out-Of-Distribution (OOD) samples do not follow thedistribution of training set, and therefore the predicted class labels on OODsamples become meaningless. Classification-based methods have been proposed forOOD detection; however, in this study we show that this type of method has notheoretical guarantee and is practically breakable by our OOD Attack algorithmbecause of dimensionality reduction in the DNN models. We also show that Glowlikelihood-based OOD detection is breakable as well.

An Algorithm for Out-Of-Distribution Attack to Neural Network Encoder